@article{aircacheactivatingintermodalrelevancykv,
  title = {AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference},
  author = {Kai Huang and Hao Zou and Bochen Wang and Ye Xi and Zhen Xie and Hao Wang},
  year = {2025},
  eprint = {2503.23956},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.23956v1},
}